Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18709
    Prev
    Next
    INDEX
    Explanations

    key phrases and statements related to regulations and compliance in formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.02
    2:0.14
    3:0.08
    4:0.06
    5:0.07
    6:0.06
    7:0.05
    8:0.21
    9:0.06
    10:0.02
    11:0.02
    Negative Logits
    atown
    -3.29
     Dickens
    -3.23
     Kinder
    -3.02
     Marketplace
    -3.02
     malls
    -2.93
    Rog
    -2.87
     haw
    -2.87
     Kushner
    -2.87
     shovel
    -2.80
    House
    -2.80
    POSITIVE LOGITS
     UC
    5.11
     Gian
    4.21
     doping
    4.19
     FIA
    4.12
    UC
    3.91
     Ferrari
    3.78
     Alberto
    3.70
     Sport
    3.60
     Italy
    3.47
     Athlet
    3.44
    Activations Density 0.006%

    No Known Activations